Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    track listing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mathematic
    -0.07
     ник
    -0.07
     chemical
    -0.06
     Beng
    -0.06
    .doc
    -0.06
     основе
    -0.06
     aure
    -0.06
     kiện
    -0.06
     undergraduate
    -0.06
    igsaw
    -0.06
    POSITIVE LOGITS
    .twitter
    0.08
     请求
    0.07
     clauses
    0.07
     Rarity
    0.07
     Logo
    0.07
     לקבל
    0.07
    recur
    0.07
    Truthy
    0.07
    _markup
    0.07
    ((↵
    0.07
    Act Density 0.001%

    No Known Activations